opensea-tool-sdk

Build, register, and gate AI-callable tool endpoints using the OpenSea Tool Registry (ERC-8257) on Base. Scaffold HTTPS tools with JSON Schema interfaces, register them onchain, gate access via NFT ownership, subscriptions, trait gating, or x402 pay-per-call (USDC), and call gated tools. For querying OpenSea marketplace data use opensea-api instead.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill body with clear sequencing, validation gates, and sound progressive disclosure through three reference files. Its only meaningful weakness is conciseness: repeated example blocks and an over-detailed inline Discovery reference could be tightened.

Suggestions

Consolidate Examples A–F by factoring the shared register/auth/pay CLI patterns into one parameterized example, then show only the gate-specific differences per scenario.

Consider moving the full Tool Discovery API parameter tables and curl set into a reference file, keeping just the key endpoints and the API-key resolution snippet inline.

Trim redundancy between the response-codes table and the CLI command table (e.g. `pay`/`auth` header behavior) to reduce duplicated detail.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of basic-concept padding, but it could be tightened: Examples A–F repeat near-identical register/auth/pay CLI invocations, and the Tool Discovery section inlines five curl examples plus three parameter tables that partly duplicate each other.	2 / 3
Actionability	Provides copy-paste-ready guidance throughout — concrete `npx @opensea/tool-sdk` CLI commands, full TypeScript handler/manifest snippets, curl calls, contract addresses, and a detailed CLI flag table.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced (1a–1d scaffolding, a numbered six-step registration flow that explicitly 'Validates the manifest schema', and numbered end-to-end examples) with validation gates available via `--dry-run`, `validate`, and `verify`.	3 / 3
Progressive Disclosure	Heavy protocol mechanics are delegated to three real, one-level-deep reference files (x402.md, predicate-gating.md, known-predicates.md), each well-signaled inline and summarized in a References section, while the core create/register/gate/call workflow stays in the overview.	3 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with a clear niche and a useful scope-out pointer, written in third person. Its main weakness is the absence of an explicit 'Use when…' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when…' trigger clause listing the natural situations that should invoke this skill (e.g. 'Use when you need to scaffold, register, or gate an AI-callable tool endpoint on Base') to raise completeness to 3.

Surface one or two plain-language trigger keywords earlier in the description so the clause reads naturally as something a user would say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build, register, and gate', 'Scaffold HTTPS tools with JSON Schema interfaces', 'gate access via NFT ownership, subscriptions, trait gating, or x402 pay-per-call (USDC)', 'call gated tools' — matching the top anchor for specific concrete actions.	3 / 3
Completeness	The 'what' is explicit but there is no 'Use when…' trigger clause; only a scope-out pointer ('For querying OpenSea marketplace data use opensea-api instead'), so the judging guideline caps completeness at 2.	2 / 3
Trigger Term Quality	Good coverage of natural domain terms a user would say ('register them onchain', 'gate access', 'NFT ownership', 'subscriptions', 'x402 pay-per-call') and uses third-person voice, so no voice penalty applies.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (OpenSea Tool Registry / ERC-8257 tool endpoints) and explicitly hands off marketplace queries to 'opensea-api', making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (561 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: ProjectOpenSea/opensea-skill
Commit: 142f269

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.